From 2bc9e82465d1d9f1323cf3f1c93b953fe1cc36ba Mon Sep 17 00:00:00 2001 From: Jeremy Metz Date: Mon, 23 Feb 2015 16:40:38 +0000 Subject: [PATCH] Minor stylistic changes, removed lena test --- skimage/filters/tests/test_thresholding.py | 4 ---- skimage/filters/thresholding.py | 11 ++++------- 2 files changed, 4 insertions(+), 11 deletions(-) diff --git a/skimage/filters/tests/test_thresholding.py b/skimage/filters/tests/test_thresholding.py index c360a030..a47b6f20 100644 --- a/skimage/filters/tests/test_thresholding.py +++ b/skimage/filters/tests/test_thresholding.py @@ -179,10 +179,6 @@ def test_li_coins_image_as_float(): assert 0.37 < threshold_li(coins) < 0.38 -def test_li_lena_image(): - img = skimage.img_as_ubyte(data.lena()) - assert 127 < threshold_li(img) < 129 - def test_li_astro_image(): img = skimage.img_as_ubyte(data.astronaut()) assert 66 < threshold_li(img) < 68 diff --git a/skimage/filters/thresholding.py b/skimage/filters/thresholding.py index d5907f8e..2921017b 100644 --- a/skimage/filters/thresholding.py +++ b/skimage/filters/thresholding.py @@ -324,7 +324,7 @@ def threshold_li(image): .. [1] Li C.H. and Lee C.K. (1993) "Minimum Cross Entropy Thresholding" Pattern Recognition, 26(4): 617-625 .. [2] Li C.H. and Tam P.K.S. (1998) "An Iterative Algorithm for Minimum - Cross Entropy Thresholding"Pattern Recognition Letters, 18(8): 771-776 + Cross Entropy Thresholding" Pattern Recognition Letters, 18(8): 771-776 .. [3] Sezgin M. and Sankur B. (2004) "Survey over Image Thresholding Techniques and Quantitative Performance Evaluation" Journal of Electronic Imaging, 13(1): 146-165 @@ -340,10 +340,10 @@ def threshold_li(image): >>> thresh = threshold_li(image) >>> binary = image <= thresh """ - # Requires positive image ( log(mean)) + # Requires positive image (because of log(mean)) offset = image.min() - # Can't use fixed tolerance for float image - imrange = image.max()-offset + # Can not use fixed tolerance for float image + imrange = image.max() - offset image -= offset tolerance = 0.5 * imrange / 256.0 @@ -360,9 +360,7 @@ def threshold_li(image): old_thresh = new_thresh threshold = old_thresh + tolerance # range # Calculate the means of background and object pixels - # Background mean_back = image[image <= threshold].mean() - # Object mean_obj = image[image > threshold].mean() temp = (mean_back - mean_obj) / (np.log(mean_back) - np.log(mean_obj)) @@ -373,4 +371,3 @@ def threshold_li(image): new_thresh = temp + tolerance return threshold + offset -